Evals for Every Language - Language lv: leaderboard
Metric: Average Score (%). Source: huggingface.co. 71 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 72.54 |
| 2 | Gemini 3.1 Pro (Preview) | 72.04 |
| 3 | GPT-5.1 | 70.31 |
| 4 | GPT-5.2 | 69.66 |
| 5 | GPT-5 | 69.44 |
| 6 | GPT-5.3 | 68.65 |
| 7 | Claude Opus 4.8 | 68.64 |
| 8 | DeepSeek V3.1 | 68.64 |
| 9 | Claude Sonnet 4.5 | 68.56 |
| 10 | GPT-5.5 | 68.55 |
| 11 | Gemini 2.5 Pro | 67.6 |
| 12 | Claude Sonnet 4.6 | 67.45 |
| 13 | Claude Sonnet 4 | 66.94 |
| 14 | Nova Pro (v1) | 66.5 |
| 15 | GPT-4o | 66.17 |
Interactive version: theaggregate.ai/benchmark?slug=evals-for-every-language-language-lv · How It Works · Data refreshed daily, snapshot 2026-09-05.